agentleFS
Sign inStart free
adriano-labsadriano-labs/applyarc-claude-plugin/skills/cv-bullet-writer/SKILL.md

cv-bullet-writer

Skill0 starsChanged 30 days agoMITView on GitHub

Turns CV duties into strong, honest impact bullets using ApplyArc's free bullet rewriter. Asks for real numbers or honest ranges, offers versions that add numbers, power up wording, match a job posting or cut length, and shows a before and after strength score. Works without an ApplyArc account. Use when the user says "improve this bullet", "make my CV stronger", "quantify this", "rewrite my experience", "my CV sounds weak" or pastes CV lines.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never invent numbers or results: If a bullet lacks a result, ask: how many, how much, how often, how fast, compared with what?

    line 14
  2. Very specific:

    Call rewrite_cv_bullet with the bullet, mode, role and any real numbers the user gave (fold them into bulletText).

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CV bullet writer

Rewrite CV bullets so each one shows what the user did and what changed because of it. Uses rewrite_cv_bullet from the ApplyArc MCP server (applyarc), which needs no account.

Ground rules

  1. Never invent numbers or results. If a bullet lacks a result, ask: how many, how much, how often, how fast, compared with what? Accept honest ranges ("about 30 a week") or non-numeric proof (adopted by three teams). Otherwise mark needs number.
  2. One bullet per call. rewrite_cv_bullet takes one bullet of at least three words.
  3. Keep the user's facts and voice. Offer the rewrite; the user chooses.
  4. British English. No em dashes.

Pick the mode

User wantsmode
Generally stronger wordingpower-up (default)
A number in itadd-numbers (ask for the real figure first)
To fit a job postingmatch-job, with jobDescription
Shortermake-concise

Pass role when known; it sharpens the wording.

Workflow

  1. Collect the bullets. If the user is signed in and wants their stored CV used, call get_my_profile and pick the weakest lines together.
  2. For each bullet, ask one question to surface a result if it has none.
  3. Call rewrite_cv_bullet with the bullet, mode, role and any real numbers the user gave (fold them into bulletText).
  4. Show before, after and the strength scores returned. If the rewrite added a claim the user did not give, remove it before showing.
  5. Offer a second mode if useful (for example make-concise after add-numbers).

A strong bullet

Action verb, what you did, scale, result. For example: "Rebuilt the weekly rota in Excel, cutting agency shifts by about 20% over six months." Avoid "responsible for", "helped with" and lists of duties.

Limits

The free rewriter has a daily limit per user. If a limit message comes back, show it as written. For whole-CV tailoring to a job, hand off to job-application, which uses the signed-in resume-optimizer tool.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free